A video data security protection method and device

Abstract

The present application discloses a method and system for security protection based on video data, which relates to the field of data processing technology. The method and system for security protection based on video data include: obtaining surveillance videos and associated data of surveillance videos; the associated data include various types of user evaluation data for surveillance videos; based on the associated data, determining multiple analysis keywords corresponding to the surveillance videos; based on the multiple analysis keywords, determining the analysis strategy for the surveillance videos; based on the analysis strategy, the associated relationship and the surveillance videos, determining the analysis results corresponding to the multiple analysis keywords respectively; based on the analysis results, determining the security protection strategy for the surveillance scene corresponding to the surveillance video, and feeding back the security protection strategy. The method and system for security protection based on video data can realize security protection of surveillance scenes based on the analysis results of surveillance videos.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for protecting video data security. Background Art

[0002] With the development of computer technology, data processing technology has also developed. There are also various ways to process surveillance videos. The current surveillance video processing method is usually an offline processing method that cannot be associated with the actual surveillance scene; therefore, the applicability of surveillance video processing is poor. Summary of the invention

[0003] The purpose of this application is to provide a method and device based on video data security protection, which can achieve security protection of monitoring scenes based on the analysis results of monitoring videos, while ensuring the security of monitoring scenes, while improving the applicability of monitoring video analysis results.

[0004] To achieve the above-mentioned purpose, an embodiment of the present application provides a method for security protection based on video data, including: obtaining a surveillance video and associated data of the surveillance video; the associated data includes multiple types of user evaluation data for the surveillance video; based on the associated data, determining multiple analysis keywords corresponding to the surveillance video; based on the multiple analysis keywords, determining an analysis strategy for the surveillance video; wherein the analysis strategy includes: at least one of a target analysis object, a target analysis behavior, and additional analysis information; there is an association relationship between the multiple analysis keywords, the target analysis object, the target analysis behavior, and the additional analysis information; based on the analysis strategy, the association relationship, and the surveillance video, determining the analysis results corresponding to the multiple analysis keywords respectively; based on the analysis results, determining the security protection strategy for the monitoring scene corresponding to the surveillance video, and feeding back the security protection strategy.

[0005] In a possible implementation, determining multiple analysis keywords corresponding to the surveillance video based on the associated data includes: determining a first analysis keyword corresponding to the surveillance video based on a preset keyword library and the associated data; obtaining an associated surveillance video corresponding to the surveillance video; wherein the associated surveillance video corresponds to analysis data; determining a second analysis keyword corresponding to the surveillance video based on the analysis data; and determining multiple analysis keywords corresponding to the surveillance video based on the first analysis keyword and the second analysis keyword.

[0006] In a possible implementation, the determining of multiple analysis keywords corresponding to the surveillance video based on the first analysis keyword and the second analysis keyword includes: determining the same analysis keywords and different analysis keywords in the first analysis keyword and the second analysis keyword; for the same analysis keyword, judging whether the appearance frequency of the same analysis keyword in the associated data is greater than a preset appearance frequency; if the appearance frequency of the same analysis keyword in the associated data is greater than the preset appearance frequency, determining the associated analysis keyword corresponding to the same analysis keyword; wherein the associated analysis keyword does not belong to the different analysis keywords; and determining the final analysis keyword based on the same analysis keyword, the associated analysis keyword and the different analysis keyword.

[0007] In a possible implementation, determining the analysis strategy of the surveillance video based on the multiple analysis keywords includes: determining keyword types corresponding to the multiple analysis keywords respectively; the keyword types include: object, object behavior, object evaluation and object behavior evaluation; for the object type, determining the object and an object having an association relationship with the object as the target analysis object; for the object behavior type, determining the object behavior and object behavior having an association relationship with the object behavior as the target analysis behavior; determining the object evaluation and the object behavior evaluation as additional analysis information.

[0008] In a possible implementation, the video data security protection method further includes: determining a first association relationship according to the keyword types corresponding to the multiple analysis keywords respectively; the first association relationship is used to characterize the association relationship between the analysis keyword and the target analysis object, as well as the association relationship between the analysis keyword and the target analysis behavior, and the association relationship between the analysis keyword and the additional analysis information; determining a second association relationship according to the first association relationship; the second association relationship is used to characterize the association relationship between the target analysis object and the target analysis behavior, as well as the association relationship between the target analysis object and the additional analysis information; wherein, if the target analysis object is associated with the same analysis keyword as the target analysis behavior, then the target analysis object and the target analysis behavior have an association relationship; if the target analysis object and the additional analysis information are associated with the same type of analysis keyword, then the target analysis object and the additional analysis information have an association relationship.

[0009] In a possible implementation, the analysis results corresponding to the multiple analysis keywords are determined based on the analysis strategy and the association relationship, including: if the analysis strategy includes a target analysis object, a target analysis behavior, and additional analysis information, the object analysis result is determined based on the object analysis model and the surveillance video; the behavior analysis result is determined based on the behavior analysis model and the surveillance video; the additional information analysis result is determined based on the event analysis model and the surveillance video; the final analysis result is determined based on the object analysis result, the behavior analysis result, and the additional information analysis result; and the analysis results corresponding to the multiple keywords are determined based on the association relationship and the final analysis result.

[0010] In one possible implementation, the analysis result is used to characterize whether there are abnormal objects in the monitoring scene, and to characterize whether there is an abnormal number of objects in the monitoring scene. The method of determining the security protection strategy for the monitoring scene corresponding to the monitoring video based on the analysis result includes: if the analysis result characterizes that there are abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is not abnormal, determining that the security protection strategy is: evacuating the objects in the monitoring scene, and dispatching security protection personnel to the monitoring scene; if the analysis result characterizes that there are no abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is abnormal, determining that the security protection strategy is: limiting the number of objects entering the monitoring scene, and playing a first preset prompt message, wherein the first preset prompt message is used to instruct leaving the monitoring scene.

[0011] In a possible implementation, the video data-based security protection method also includes: if the analysis result indicates that there are abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is abnormal, determining the security protection strategy as follows: evacuating the objects in the monitoring scene, dispatching security protection personnel to the monitoring scene, stopping new objects from entering the monitoring scene, and playing a second preset prompt message, wherein the second preset prompt message is used to indicate leaving the monitoring scene under the guidance of the security protection personnel; if the analysis result indicates that there are no abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is not abnormal, determining the security protection strategy as follows: playing a third preset prompt message, wherein the third preset prompt message is used to indicate that there is currently no abnormality in the monitoring scene.

[0012] In a possible implementation, the video data security protection method also includes: for the first evaluation data of the first type of user on the surveillance video, determining the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data; if the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is greater than a preset matching degree, displaying the first evaluation data to the viewing users of the surveillance video in a target display form, and the target display form is different from the display form of other evaluation data; for the second evaluation data of the second type of user on the surveillance video, determining whether the support rate corresponding to the second evaluation data is higher than a preset support rate; wherein the support rate is determined based on the number of views and / or the number of likes; if the support rate corresponding to the second evaluation data is higher than the preset support rate, displaying the analysis result corresponding to the second evaluation data as the reply data of the second evaluation data; if the support rate corresponding to the second evaluation data is lower than the preset support rate, displaying the second evaluation data and the analysis result corresponding to the second evaluation data as hidden information of the surveillance video; wherein the hidden information is used for display when responding to a display request.

[0013] An embodiment of the present application also provides a security protection system based on video data, including: a video analysis module, configured to: obtain a surveillance video and associated data of the surveillance video; the associated data includes multiple types of user evaluation data for the surveillance video; based on the associated data, determine multiple analysis keywords corresponding to the surveillance video; based on the multiple analysis keywords, determine the analysis strategy of the surveillance video; wherein the analysis strategy includes: at least one of a target analysis object, a target analysis behavior and additional analysis information; there is an association relationship between the multiple analysis keywords, the target analysis object, the target analysis behavior and the additional analysis information; based on the analysis strategy, the association relationship and the surveillance video, determine the analysis results corresponding to the multiple analysis keywords respectively; a security protection module, configured to: based on the analysis results, determine the security protection strategy of the monitoring scene corresponding to the surveillance video, and feedback the security protection strategy.

[0014] Compared with the prior art, the video data security protection method and system provided in the embodiment of the present application obtains the associated data of the surveillance video, and the associated data includes various types of user evaluation data for the surveillance video. Based on the associated data, multiple analysis keywords can be determined, and then the analysis strategy is determined using the multiple analysis keywords. Thus, the surveillance video is analyzed using the analysis strategy and the association relationship between the various information in the analysis strategy, and the analysis results corresponding to the multiple analysis keywords are determined. Through this analysis method, a more targeted analysis can be achieved, and the security of the surveillance video analysis results can be improved. In addition, the obtained analysis results are associated with the analysis keywords, and can be used to determine the security protection strategy of the surveillance scene corresponding to the surveillance video, and realize the security protection of the surveillance scene. Therefore, the technical solution can realize the security protection of the surveillance scene based on the analysis results of the surveillance video, and improve the applicability of the surveillance video analysis results while ensuring the security of the surveillance scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of an application scenario according to an embodiment of the present application;

[0016] Figure 2 is a flow chart of a video data security protection method according to an embodiment of the present application;

[0017] Figure 3 It is a structural schematic diagram of a video data security protection system according to an embodiment of the present application;

[0018] Figure 4 It is a schematic diagram of the structure of a terminal device according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] The specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present application is not limited by the specific implementation methods.

[0020] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0021] The technical solution provided in the embodiments of the present application can be applied to various analysis scenarios of surveillance videos. In these analysis scenarios, the analysis results of the surveillance videos are used to perform security protection on the surveillance scenes.

[0022] It can be understood that the monitoring scenarios are various monitorable environments, such as squares, shopping malls, etc.

[0023] In the embodiment of the present application, the surveillance video may be surveillance data of different scenes and may involve multiple objects.

[0024] In some application scenarios, surveillance videos may have different types of viewers, some of whom may be professional, while others may not be professional and can only make subjective judgments. Different viewing users may have different comment data on surveillance videos.

[0025] Currently, the analysis method of surveillance videos is usually offline analysis, which is not associated with the actual surveillance scene, resulting in poor applicability of the surveillance video analysis results.

[0026] Based on this, the embodiments of the present application provide a security protection solution based on surveillance video analysis, which implements security protection of surveillance scenes based on the analysis results of surveillance videos, thereby improving the applicability of surveillance video analysis results while ensuring the security of surveillance scenes.

[0027] Furthermore, the hardware operating environment of the technical solution of the embodiment of the present application can be a security protection platform for monitoring scenarios.

[0028] In some embodiments, Figure 1 As shown, the security protection platform is connected to the video monitoring platform in communication, so that the security protection platform can obtain information from the video monitoring platform to process the monitoring video. In addition, the security protection platform can also feed back the processing results to the video monitoring platform to apply the processing results.

[0029] Please refer to the following Figure 2 , is a flow chart of a video data security protection method provided in an embodiment of the present application, the video data security protection method comprising:

[0030] Step 201, obtaining surveillance videos and associated data of the surveillance videos, wherein the surveillance videos are surveillance videos, and the associated data include various types of user evaluation data on the surveillance videos.

[0031] In some embodiments, there are multiple types of users, such as users who watch surveillance videos. The professionalism of the users may be different. For example, in a monitoring scene for a game, the users may be game commentators, game coaches, game fans, etc.

[0032] In some embodiments, the evaluation data may be real-time evaluation data, such as bullet screen, floating screen, etc., or non-real-time evaluation data, such as video comments, video messages, etc. Or, other forms of evaluation data that can be obtained.

[0033] In some embodiments, these evaluation data can come from the monitoring video playback platform, so these data can be easily obtained. In addition, these evaluation data correspond to various information such as the evaluation user, the evaluation user type, the evaluation method, and the evaluation content.

[0034] Step 202: Determine multiple analysis keywords corresponding to the surveillance video based on the associated data.

[0035] It can be understood that the multiple analysis keywords are information extracted from these related data. Therefore, the multiple analysis keywords can represent the analysis information of the surveillance video that different types of users want to see.

[0036] As an optional implementation, step 202 includes: determining a first analysis keyword corresponding to the surveillance video based on a preset keyword library and associated data; obtaining an associated surveillance video corresponding to the surveillance video; wherein the associated surveillance video corresponds to analysis data; determining a second analysis keyword corresponding to the surveillance video based on the analysis data; and determining multiple analysis keywords corresponding to the surveillance video based on the first analysis keyword and the second analysis keyword.

[0037] In some embodiments, based on a preset keyword library, keywords are extracted for each piece of evaluation data to determine the analysis keywords corresponding to each piece of evaluation data. Then, these analysis keywords are deduplicated and the obtained analysis keywords are the first analysis keywords.

[0038] In some embodiments, the preset keyword library is a preconfigured keyword library, in which a plurality of keywords associated with the surveillance video are stored, for example, keywords corresponding to information such as object names, object behaviors, and object events.

[0039] In some embodiments, the associated surveillance video corresponding to the surveillance video can be obtained from a big data platform (a platform that stores a large number of surveillance videos).

[0040] In some embodiments, the monitoring video and the associated monitoring video have some common features. For example, for a game monitoring scenario, these features may be: the same team, the same game format, the same referee, etc. For example, if the monitoring video is a second-half monitoring video, the associated monitoring video may be a first-half monitoring video, etc.

[0041] In some embodiments, the associated surveillance video corresponds to analysis data, and the analysis data may be analysis data issued by a professional analyst or provided by a big data platform, and the analysis method of the analysis data is not limited.

[0042] In some embodiments, based on the analysis data, keywords are extracted therefrom to determine the second analysis keyword. Based on the analysis data, a preset keyword library can also be used to determine the second analysis keyword.

[0043] Furthermore, based on the first analysis keyword and the second analysis keyword, a plurality of analysis keywords corresponding to the surveillance video are determined.

[0044] As an optional implementation, based on the first analysis keyword and the second analysis keyword, multiple analysis keywords corresponding to the surveillance video are determined, including: determining the same analysis keywords and different analysis keywords in the first analysis keyword and the second analysis keyword; for the same analysis keyword, judging whether the appearance frequency of the same analysis keyword in the associated data is greater than the preset appearance frequency; if the appearance frequency of the same analysis keyword in the associated data is greater than the preset appearance frequency, determining the associated analysis keywords corresponding to the same analysis keyword; wherein the associated analysis keywords do not belong to the different analysis keywords; and determining the final analysis keywords based on the same analysis keywords, the associated analysis keywords and the different analysis keywords.

[0045] In some embodiments, the first analysis keyword and the second analysis keyword are compared to determine the same analysis keywords and different analysis keywords. The similarity between the first analysis keyword and the second analysis keyword can be calculated, and if the similarity is greater than a preset similarity, the two keywords are considered to be the same. It can be understood that the same here is not absolutely the same.

[0046] In some embodiments, for the same analysis keyword, its occurrence frequency in the associated data is determined, and if the occurrence frequency is greater than a preset occurrence frequency, the associated analysis keyword corresponding to the same analysis keyword is determined. The preset occurrence frequency can be set according to different application scenarios and is not limited here.

[0047] In some embodiments, the associated analysis keyword corresponding to the same analysis keyword may be a keyword that appears together with the same analysis keyword in the associated data more than a preset number of times. That is, each time the same analysis keyword appears in the associated data, the associated analysis keyword will also appear. The preset number of times can be set according to different application scenarios and is not limited here.

[0048] It can be understood that the associated analysis keyword does not belong to the different analysis keyword, and its associated analysis keyword does not overlap with the different analysis keyword.

[0049] Furthermore, the final analysis keywords are determined based on the same analysis keywords, related analysis keywords, and different analysis keywords. Among them, these three keywords can be integrated, for example: the similarity between these keywords is calculated, and if the similarity between two keywords is greater than a threshold, only one of the keywords can be retained, etc. For another example, it is determined whether the total number of keywords is greater than a threshold. If so, some of the keywords are deleted. When deleting, related analysis keywords and different analysis keywords are deleted first; and among different analysis keywords, analysis keywords determined based on the second analysis keyword are deleted first.

[0050] Step 203: Determine an analysis strategy for the surveillance video based on multiple analysis keywords.

[0051] The analysis strategy includes: at least one of a target analysis object, a target analysis behavior, and additional analysis information; and a correlation relationship exists between multiple analysis keywords, target analysis objects, target analysis behaviors, and additional analysis information.

[0052] In some embodiments, based on multiple analysis keywords, an analysis strategy for a surveillance video is determined, including: determining keyword types corresponding to the multiple analysis keywords; keyword types include: object, object behavior, object evaluation, and object behavior evaluation; for object type, determining the object and an object having an association with the object as target analysis objects; for object behavior type, determining the object behavior and object behavior having an association with the object behavior as target analysis behavior; and determining the object evaluation and object behavior evaluation as additional analysis information.

[0053] In some embodiments, the keyword types corresponding to the multiple analysis keywords may be determined based on a preset keyword classification model. The preset keyword classification model may be determined by training based on a keyword set labeled with keyword types. The specific training method is not introduced in detail here, and reference may be made to mature technologies in the art.

[0054] In some embodiments, the keyword types include object, object behavior, object evaluation, and object behavior evaluation. Among them, object evaluation is used to represent the evaluation of the performance of an object; object behavior evaluation is used to represent the evaluation of a behavior.

[0055] In some embodiments, with respect to the object type, the object and objects associated with the object are determined as target analysis objects, wherein the objects associated with the object may be teammates of the object or opponents of the object.

[0056] In some embodiments, for the object behavior type, the object behavior and the object behavior associated with the object behavior are determined as target analysis behaviors. The object behavior associated with the object behavior may be a continuous object behavior, for example, after successfully intercepting the ball, there is usually a pass or a pitch, etc. These object behaviors may be considered to have an associated relationship.

[0057] In some embodiments, the object evaluation and the object behavior evaluation are directly determined as additional analysis information.

[0058] In some embodiments, since there is an association relationship between the analysis keyword, the target analysis object, the target analysis behavior and the additional analysis information, the association relationship needs to be determined.

[0059] Therefore, as an optional implementation, the method also includes: determining a first association relationship based on keyword types corresponding to multiple analysis keywords; the first association relationship is used to characterize the association relationship between the analysis keyword and the target analysis object, as well as the association relationship between the analysis keyword and the target analysis behavior, and the association relationship between the analysis keyword and additional analysis information; determining a second association relationship based on the first association relationship; the second association relationship is used to characterize the association relationship between the target analysis object and the target analysis behavior, as well as the association relationship between the target analysis object and the additional analysis information; wherein, if the analysis keywords associated with the target analysis object and the target analysis behavior are the same, then the target analysis object and the target analysis behavior have an association relationship; if the types of analysis keywords associated with the target analysis object and the additional analysis information are the same, then the target analysis object and the additional analysis information have an association relationship.

[0060] Among them, based on the fact that the keyword types corresponding to multiple analysis keywords are known, the association relationship between them and the target analysis object, target analysis behavior and additional analysis information can be directly determined. For example, if the keyword type corresponding to the analysis keyword is object, and the object is consistent with the target analysis object, then it has an association relationship with the target analysis object. If the keyword type corresponding to the analysis keyword is object behavior, and the object behavior is consistent with the target analysis behavior, then it has an association relationship with the target analysis object. The same applies to the additional analysis information.

[0061] Further, based on the first association relationship, a second association relationship may be determined. In some embodiments, if the target analysis object and the target analysis behavior are associated with the same analysis keyword, then the target analysis object and the target analysis behavior have an association relationship; if the target analysis object and the additional analysis information are associated with the same type of analysis keyword, then the target analysis object and the additional analysis information have an association relationship.

[0062] Step 204: Determine analysis results corresponding to the plurality of analysis keywords based on the analysis strategy, the association relationship and the surveillance video.

[0063] In some embodiments, step 204 includes: if the analysis strategy includes a target analysis object, a target analysis behavior, and additional analysis information, determining the object analysis result based on the object analysis model and the surveillance video; determining the behavior analysis result based on the behavior analysis model and the surveillance video; determining the additional information analysis result based on the event analysis model and the surveillance video; determining the final analysis result based on the object analysis result, the behavior analysis result, and the additional information analysis result; and determining the analysis results corresponding to multiple keywords based on the association relationship.

[0064] In some embodiments, the preset object analysis model, behavior analysis model and event analysis model can all be neural network models, which are trained using corresponding training data sets. The specific training method can refer to mature technologies in the art.

[0065] Furthermore, the object analysis results can be determined using the object analysis model; from the object analysis results, the analysis results of the target analysis object can be extracted, which can be used as the analysis results of the keywords associated with the target analysis object.

[0066] Furthermore, the behavior analysis model can be used to determine the behavior analysis results; from the behavior analysis results, the analysis results of the target analysis behavior are extracted, which can be used as the analysis results of the keywords associated with the target analysis behavior.

[0067] Furthermore, the event analysis result can be determined by using the event analysis model; and the additional information analysis result can be extracted from the event analysis result, which can be used as the analysis result of the keyword associated with the additional information analysis result.

[0068] Therefore, based on the object analysis results, the behavior analysis results and the additional information analysis results, the final analysis results can be determined; and based on the association relationship and the final analysis results, the analysis results corresponding to the multiple keywords are determined.

[0069] In some embodiments, based on the association relationship and the final analysis result, the analysis results corresponding to each keyword can be determined.

[0070] In some embodiments, after the analysis results corresponding to the multiple keywords are determined, the analysis results may be utilized.

[0071] Step 205: Based on the analysis result, determine the security protection strategy for the surveillance scene corresponding to the surveillance video, and provide feedback on the security protection strategy.

[0072] As an optional implementation, the analysis result is used to characterize whether there are abnormal objects in the monitoring scene, and to characterize whether there is an abnormal number of objects in the monitoring scene. Step 205 may include: if the analysis result characterizes that there are abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is not abnormal, determining the safety protection strategy is: evacuating the objects in the monitoring scene, and dispatching security protection personnel to the monitoring scene; if the analysis result characterizes that there are no abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is abnormal, determining the safety protection strategy is: limiting the number of objects entering the monitoring scene, and playing a first preset prompt message, and the first preset prompt message is used to instruct leaving the monitoring scene.

[0073] In other embodiments, if the analysis result indicates that there are abnormal objects in the monitoring scene, and there is an abnormal number of objects in the monitoring scene, the safety protection strategy is determined to be: evacuate the objects in the monitoring scene, dispatch security personnel to the monitoring scene, stop new objects from entering the monitoring scene, and play a second preset prompt message, the second preset prompt message is used to instruct to leave the monitoring scene under the guidance of the security personnel; if the analysis result indicates that there are no abnormal objects in the monitoring scene, and there is no abnormal number of objects in the monitoring scene, the safety protection strategy is determined to be: play a third preset prompt message, the third preset prompt message is used to indicate that there is no abnormality in the monitoring scene.

[0074] In some embodiments, the security protection strategy can be fed back to the playback end of the monitoring video, or the security protection end of the monitoring scene, etc.

[0075] In some embodiments, the analysis-related information of the surveillance video can also be fed back at the front end so that the viewing user has corresponding feedback information. Therefore, as an optional implementation, the method further includes: for the first evaluation data of the surveillance video by the first type of user, judging the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data; if the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is greater than the preset matching degree, displaying the first evaluation data to the viewing user of the surveillance video in a target display form, and the target display form is different from the display form of other evaluation data; for the second evaluation data of the surveillance video by the second type of user, judging whether the support rate corresponding to the second evaluation data is higher than the preset support rate; wherein the support rate is determined based on the number of views and / or the number of likes; if the support rate corresponding to the second evaluation data is higher than the preset support rate, displaying the analysis result corresponding to the second evaluation data as the reply data of the second evaluation data; if the support rate corresponding to the second evaluation data is lower than the preset support rate, displaying the second evaluation data and the analysis result corresponding to the second evaluation data as the hidden information of the surveillance video; wherein the hidden information is used to be displayed when responding to the display request.

[0076] In some embodiments, the first type of user may be the aforementioned professional basketball user, such as a commentator, coach, etc.

[0077] In some embodiments, the second type of users may be the aforementioned ordinary users, such as basketball fans.

[0078] In some embodiments, the preset matching degree can be set according to different application scenarios and is not limited here.

[0079] In some embodiments, if the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is greater than the preset matching degree, it means that the reference value of the first evaluation data is relatively high, and the evaluation data can be displayed in a target display form. The target display form can be special and different from the display forms of other evaluation data. For example: floating screen display, enlarged display, etc.

[0080] In some embodiments, if the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is less than the preset matching degree, it means that the reference value of the first evaluation data is not that great. At this time, the first evaluation data and the analysis result corresponding to the first evaluation data can be displayed to the user watching the surveillance video; so that the viewing user can see the analysis data from different levels. Among them, the display priority of the first evaluation data is lower than the display priority of the analysis result corresponding to the first evaluation data. That is, the analysis result corresponding to the first evaluation data is displayed first.

[0081] In some embodiments, for the second evaluation data of the second type of user on the surveillance video, it is determined whether the support rate corresponding to the second evaluation data is higher than a preset support rate; wherein the support rate is determined based on the number of views and / or the number of likes; if the support rate corresponding to the second evaluation data is higher than the preset support rate, the analysis result corresponding to the second evaluation data is displayed as reply data of the second evaluation data; if the support rate corresponding to the second evaluation data is lower than the preset support rate, the second evaluation data and the analysis result corresponding to the second evaluation data are used as hidden information of the surveillance video; wherein the hidden information is used for display when responding to a display request.

[0082] In some embodiments, the support rate is determined based on the number of views and / or the number of likes, for example, by taking a weighted average, an arithmetic average, etc. of the number of views and the number of likes.

[0083] In some embodiments, the preset support rate can be set according to different application scenarios and is not limited here.

[0084] In some embodiments, different users can customize different hidden information display interfaces. When a user opens the hidden information display interface, it can be regarded as initiating a display request. At this time, the analysis results corresponding to the second evaluation data can be displayed as hidden surveillance video.

[0085] It can be seen from the introduction of the embodiments of the present application that the associated data of the surveillance video is obtained, and the associated data includes various types of user evaluation data for the surveillance video. Based on the associated data, multiple analysis keywords can be determined, and then the analysis strategy is determined using the multiple analysis keywords. Thus, the surveillance video is analyzed using the analysis strategy and the association relationship between the various information in the analysis strategy, and the analysis results corresponding to the multiple analysis keywords are determined. Through this analysis method, a more targeted analysis can be achieved, and the security of the surveillance video analysis results can be improved. In addition, the obtained analysis results are associated with the analysis keywords, and can be used to determine the security protection strategy of the surveillance scene corresponding to the surveillance video, and realize the security protection of the surveillance scene. Therefore, the technical solution can realize the security protection of the surveillance scene based on the analysis results of the surveillance video, while ensuring the security of the surveillance scene, improving the applicability of the surveillance video analysis results.

[0086] Please refer to the following Figure 3 , an embodiment of the present application provides a security protection system based on video data, including: a video analysis module 301, configured to: obtain a surveillance video and associated data of the surveillance video; the surveillance video is a surveillance video, and the associated data includes multiple types of user evaluation data for the surveillance video; based on the associated data, determine multiple analysis keywords corresponding to the surveillance video; based on the multiple analysis keywords, determine the analysis strategy of the surveillance video; wherein the analysis strategy includes: at least one of a target analysis object, a target analysis behavior and additional analysis information; there is an association relationship between the multiple analysis keywords, the target analysis object, the target analysis behavior and the additional analysis information; based on the analysis strategy, the association relationship and the surveillance video, determine the analysis results corresponding to the multiple analysis keywords respectively; the security protection module 302, configured to: based on the analysis result, determine the security protection strategy of the surveillance scene corresponding to the surveillance video, and feedback the security protection strategy.

[0087] The implementation of the video data security protection system can refer to the aforementioned embodiments and will not be repeated here.

[0088] like Figure 4 As shown, an embodiment of the present application also provides a terminal device, including a processor 401 and a memory 402, the processor 401 and the memory 402 are communicatively connected, and the terminal device can serve as an executor of the aforementioned video data security protection method.

[0089] The processor 401 and the memory 402 are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected through one or more communication buses or signal buses. The aforementioned video data security protection method includes at least one software function module that can be stored in the memory 402 in the form of software or firmware.

[0090] Processor 401 may be an integrated circuit chip with signal processing capability. Processor 401 may be a general-purpose processor, including a CPU (Central Processing Unit), NP (Network Processor), etc.; it may also be a digital signal processor, a dedicated integrated circuit, a readily available programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0091] The memory 402 may store various software programs and modules, such as program instructions / modules corresponding to the image processing method and apparatus provided in the embodiments of the present invention. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402, that is, implementing the method in the embodiments of the present application.

[0092] The memory 402 may include, but is not limited to, RAM (Random Access Memory), ROM (Read Only Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electric Erasable Programmable Read-Only Memory), etc.

[0093] Understandably, Figure 4 The structure shown is for illustration only. The terminal device may also include Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] The foregoing description of the specific exemplary embodiments of the present application is for the purpose of illustration and illustration. These descriptions are not intended to limit the present application to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present application and its practical application, so that those skilled in the art can realize and utilize the various exemplary embodiments of the present application and various selections and changes. The scope of the present application is intended to be limited by the claims and their equivalents.

Claims

1. A video data security protection method, characterized in that: include: Acquire surveillance video and associated data of the surveillance video; The associated data includes multiple types of user evaluation data on the surveillance video; Based on the associated data, determining a plurality of analysis keywords corresponding to the surveillance video; Based on the multiple analysis keywords, determining the analysis strategy of the surveillance video; wherein the analysis strategy includes: at least one of a target analysis object, a target analysis behavior, and additional analysis information; and there is an association relationship between the multiple analysis keywords, the target analysis object, the target analysis behavior, and the additional analysis information; Based on the analysis strategy, the association relationship and the surveillance video, determining analysis results corresponding to the multiple analysis keywords respectively; Based on the analysis result, determine the security protection strategy of the monitoring scene corresponding to the monitoring video, and provide feedback on the security protection strategy; For first evaluation data of the first type of user on the surveillance video, determining a matching degree between the first evaluation data and an analysis result corresponding to the first evaluation data; If the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is greater than a preset matching degree, the first evaluation data is displayed to the user viewing the surveillance video in a target display form, and the target display form is different from the display forms of other evaluation data; For the second evaluation data of the second type of users on the surveillance video, determining whether the support rate corresponding to the second evaluation data is higher than a preset support rate; wherein the support rate is determined based on the number of views and / or the number of likes; If the support rate corresponding to the second evaluation data is higher than the preset support rate, the analysis result corresponding to the second evaluation data is displayed as the reply data of the second evaluation data; If the support rate corresponding to the second evaluation data is lower than the preset support rate, the second evaluation data and the analysis result corresponding to the second evaluation data are used as hidden information of the surveillance video; wherein the hidden information is used for display when responding to a display request.

2. The video data security protection method according to claim 1 is characterized in that: The determining, based on the associated data, a plurality of analysis keywords corresponding to the surveillance video includes: Determine a first analysis keyword corresponding to the surveillance video based on a preset keyword library and the associated data; Obtaining an associated surveillance video corresponding to the surveillance video; wherein the associated surveillance video corresponds to analysis data; Determining a second analysis keyword corresponding to the surveillance video according to the analysis data; Based on the first analysis keyword and the second analysis keyword, a plurality of analysis keywords corresponding to the surveillance video are determined.

3. The video data security protection method according to claim 2 is characterized in that: The determining, based on the first analysis keyword and the second analysis keyword, a plurality of analysis keywords corresponding to the surveillance video includes: determining identical analysis keywords and different analysis keywords among the first analysis keywords and the second analysis keywords; For the same analysis keyword, determining whether the appearance frequency of the same analysis keyword in the associated data is greater than a preset appearance frequency; If the appearance frequency of the same analysis keyword in the associated data is greater than a preset appearance frequency, determining an associated analysis keyword corresponding to the same analysis keyword; wherein the associated analysis keyword does not belong to the different analysis keywords; A final analysis keyword is determined based on the same analysis keyword, the related analysis keyword, and the different analysis keyword.

4. The video data security protection method according to claim 1 is characterized in that: The step of determining the analysis strategy of the surveillance video based on the multiple analysis keywords includes: Determine the keyword types corresponding to the multiple analysis keywords respectively; the keyword types include: object, object behavior, object evaluation and object behavior evaluation; For the object type, determining the object and an object associated with the object as the target analysis objects; For the object behavior type, determining the object behavior and an object behavior associated with the object behavior as the target analysis behavior; The object evaluation and the object behavior evaluation are determined as additional analysis information.

5. The video data security protection method according to claim 4 is characterized in that: The video data security protection method further includes: Determine a first association relationship according to the keyword types respectively corresponding to the multiple analysis keywords; the first association relationship is used to characterize the association relationship between the analysis keyword and the target analysis object, and is used to characterize the association relationship between the analysis keyword and the target analysis behavior, and is used to characterize the association relationship between the analysis keyword and the additional analysis information; A second association relationship is determined based on the first association relationship; the second association relationship is used to characterize the association relationship between the target analysis object and the target analysis behavior, and is used to characterize the association relationship between the target analysis object and the additional analysis information; wherein, if the target analysis object and the target analysis behavior are associated with the same analysis keyword, then the target analysis object and the target analysis behavior have an association relationship; if the target analysis object and the additional analysis information are associated with the same type of analysis keyword, then the target analysis object and the additional analysis information have an association relationship.

6. The video data security protection method according to claim 1, characterized in that: The determining, based on the analysis strategy, the association relationship and the surveillance video, analysis results corresponding to the plurality of analysis keywords respectively includes: If the analysis strategy includes a target analysis object, a target analysis behavior, and additional analysis information, determining an object analysis result based on an object analysis model and the surveillance video; Determine a behavior analysis result based on the behavior analysis model and the surveillance video; Determine additional information analysis results based on the event analysis model and the surveillance video; Determining a final analysis result based on the object analysis result, the behavior analysis result and the additional information analysis result; Based on the association relationship and the final analysis result, analysis results corresponding to the multiple keywords are determined.

7. The video data security protection method according to claim 1 is characterized in that: The analysis result is used to characterize whether there are abnormal objects in the monitoring scene, and whether the number of objects in the monitoring scene is abnormal. The security protection strategy of the monitoring scene corresponding to the monitoring video is determined based on the analysis result, including: If the analysis result indicates that there are abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is not abnormal, determining the safety protection strategy is: evacuating the objects in the monitoring scene and dispatching safety protection personnel to the monitoring scene; If the analysis result indicates that there are no abnormal objects in the monitoring scene and there is an abnormal number of objects in the monitoring scene, the security protection strategy is determined to be: limiting the number of objects entering the monitoring scene and playing a first preset prompt message, wherein the first preset prompt message is used to instruct leaving the monitoring scene.

8. The video data security protection method according to claim 7 is characterized in that: The video data security protection method further includes: If the analysis result indicates that there are abnormal objects in the monitoring scene, and the number of objects in the monitoring scene is abnormal, the safety protection strategy is determined to be: evacuate the objects in the monitoring scene, dispatch safety protection personnel to the monitoring scene, stop new objects from entering the monitoring scene, and play a second preset prompt message, wherein the second preset prompt message is used to instruct the objects to leave the monitoring scene under the guidance of the safety protection personnel; If the analysis result indicates that there are no abnormal objects in the monitoring scene and there is no abnormality in the number of objects in the monitoring scene, the security protection strategy is determined to be: playing a third preset prompt information, wherein the third preset prompt information is used to indicate that there is currently no abnormality in the monitoring scene.

9. A video data security protection system, characterized in that: include: The video analysis module is configured as follows: Acquire surveillance video and associated data of the surveillance video; The associated data includes multiple types of user evaluation data on the surveillance video; Based on the associated data, determining a plurality of analysis keywords corresponding to the surveillance video; Based on the multiple analysis keywords, determining the analysis strategy of the surveillance video; wherein the analysis strategy includes: at least one of a target analysis object, a target analysis behavior, and additional analysis information; and there is an association relationship between the multiple analysis keywords, the target analysis object, the target analysis behavior, and the additional analysis information; Based on the analysis strategy, the association relationship and the surveillance video, determining analysis results corresponding to the multiple analysis keywords respectively; A security protection module is configured to: determine a security protection strategy for a surveillance scene corresponding to the surveillance video based on the analysis result, and provide feedback on the security protection strategy; The security protection module is further configured to: for first evaluation data of the first type of user on the surveillance video, determine a matching degree between the first evaluation data and an analysis result corresponding to the first evaluation data; If the matching degree between the first evaluation data and the analysis result corresponding to the first evaluation data is greater than a preset matching degree, the first evaluation data is displayed to the user viewing the surveillance video in a target display form, and the target display form is different from the display forms of other evaluation data; For the second evaluation data of the second type of users on the surveillance video, determining whether the support rate corresponding to the second evaluation data is higher than a preset support rate; wherein the support rate is determined based on the number of views and / or the number of likes; If the support rate corresponding to the second evaluation data is higher than the preset support rate, the analysis result corresponding to the second evaluation data is displayed as the reply data of the second evaluation data; If the support rate corresponding to the second evaluation data is lower than the preset support rate, the second evaluation data and the analysis result corresponding to the second evaluation data are used as hidden information of the surveillance video; wherein the hidden information is used for display when responding to a display request.

Images